INDEX
Explanations
references to a specific entity named Butler and possibly locations connected to it
mentions of the name "Butler."
New Auto-Interp
Negative Logits
udo
-0.89
arin
-0.85
sis
-0.82
eways
-0.78
eway
-0.78
lasses
-0.74
vg
-0.73
light
-0.71
clud
-0.70
ning
-0.70
POSITIVE LOGITS
Osw
0.88
Butler
0.83
McH
0.77
Hancock
0.75
flies
0.73
ipop
0.73
parts
0.72
Bulldogs
0.72
EStreamFrame
0.71
stown
0.66
Activations Density 0.029%